code-graph runs on your own machine — the client starts it, so there is no endpoint to ping. 3 259 installs a week from pypi. Last commit 20 Oct 2026.
Local dependency graph: callers, entry points and file:line evidence for what a change affects.
What the code does
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
proc = subprocess.run(["git", "-C", str(root), "-c", "color.ui=false", "-c", "core.quotepath=false", *args],
def eval(self, r, ctx: Ctx, depth=0) -> Tpl:
positionAttr.needsUpdate = true
pulses.forEach((pulse, index) => {
pulse.t = (pulse.t + dt * pulse.speed) % 1
return ("lit", v[len("unix://"):] or "/var/run/docker.sock"), None
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add cg-code-graph -- uvx cg-code-graph{
"mcpServers": {
"cg-code-graph": {
"command": "uvx",
"args": [
"cg-code-graph"
]
}
}
}[mcp_servers.cg-code-graph]
command = "uvx"
args = ["cg-code-graph"]{
"mcpServers": {
"cg-code-graph": {
"command": "uvx",
"args": [
"cg-code-graph"
]
}
}
}{
"servers": {
"cg-code-graph": {
"type": "stdio",
"command": "uvx",
"args": [
"cg-code-graph"
]
}
}
}Alternatives to code-graph
same job, measured the same wayLocal code graph for TypeScript, Python and Swift: who calls this, what breaks if I change it.
MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.
Hosted code graph over MCP: exact callers, dependencies, and cross-repo blast radius for AI agents.
Persistent, evidence-backed code graph for coding agents.
Structural code intelligence for AI agents: real call graphs, blast radius, and change history.
Hosted code graph over MCP: exact callers, dependencies, and cross-repo blast radius for AI agents.
AI code impact analysis — dependency graphs, cascade detection, and build gates for AI agents
Deterministic code map for AI coding agents: a tree-sitter call graph with exact file:line over MCP.
code-graph — questions
Answers built from our own checks of this server.